Speech recognition method with error reset commands

• US 5,781,887 A
• Filed: 10/09/1996
• Issued: 07/14/1998
• Est. Priority Date: 10/09/1996
• Status: Expired due to Term

• Current Assignee: Nokia of America Corporation (Nokia Corporation)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Juang, Biing-Hwang
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Chawan, Vijay B.
• Application Number:
  US08/728,012
• Time in Patent Office: 643 Days
• Field of Search: 704/275, 704/200, 704/248, 704/244, 704/258, 395/611, 379/67
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method for revising at least a portion of a sequence of speech data segments recognized by an automated speech recognition system. A user is prompted to vocalize the speech data segments sequentially, one speech data segment at a time. When each speech data segment is recognized it is stored as a data element and a confirmation of recognition is issued to the user. The user may then issue a verbal command to delete the last recognized data element if the confirmation indicates that a recognition error has occurred, and then repeat the last speech data element for a second recognition attempt. The user may also issue another verbal command to delete all thus-far recognized data elements in the sequence and to restart the recognition process from the beginning. If no such verbal commands are issued by the user, then the user may continue to vocalize the next sequential speech data segment.

Claims

1. A method for enabling selective revision of at least one data element identified from user vocalized speech data by an automated speech recognition apparatus through use of predetermined spoken commands issued by a user, comprising the steps of:

(a) prompting by the apparatus for user input of vocalized speech data comprising a plurality of speech data segments each representative of a data element;

(b) receiving by the apparatus one of the user vocalized speech data segments of said plural speech data segments;

(c) analyzing in the apparatus the received vocalized speech data segment to identify a data element corresponding to the received vocalized speech data segment;

(d) storing the identified data element in a memory of the apparatus;

(e) after storing of the identified data element in the memory of the apparatus,

(1) deleting by the apparatus the identified data element stored at said step (d) and returning to said step (b) for said one user vocalized speech data segment when a first spoken command, representing a user-vocalized request that input of said one user-vocalized speech data segment is to be repeated, is issued by the user and received by the apparatus; and

(2) deleting by the apparatus all identified data elements previously stored in the memory of the apparatus and returning to said step (a) when a second spoken command, representing a user-vocalized request that input of all previously stored identified data elements is to be repeated, is issued by the user and received by the apparatus; and

(f) after said step (d) and absent receipt of said first and second user-issued commands, determining by the apparatus whether all speech data segments of said plural data segments have been analyzed, and returning to said step (b) if all speech data segments of said plural data segments have not been analyzed.

2. The method of claim 1 further comprising the step of:

(g) confirming by the apparatus, after said step (d) and before said step (e), accuracy of the identification of the data element stored at said step (d) by vocalizing the stored identified data element to the user.

3. A method for enabling selective revision of at least one data element identified from user vocalized speech data by an automated speech recognition apparatus through use of a predetermined spoken command issued by a user, comprising the steps of:

(a) prompting by the apparatus for user input of vocalized speech data comprising a plurality of speech data segments each representative of a data element;

(b) receiving by the apparatus one of the user vocalized speech data segments of said plural speech data segments;

(c) analyzing in the apparatus the received vocalized speech data segment to identify a data element corresponding to the received vocalized speech data segment;

(d) storing the identified data element in a memory of the apparatus;

(e) after storing of the identified data element in the memory of the apparatus, deleting by the apparatus the identified data element stored at said step (d) and returning to said step (b) for said one user vocalized speech data segment when the predetermined spoken command, representing a user-vocalized request that input of said one user-vocalized speech data segment is to be repeated, is issued by the user and received by the apparatus; and

(f) after said step (d) and absent receipt of said user-issued command, determining by the apparatus whether all speech data segments of said plural data segments have been analyzed, and returning to said step (b) if all speech data segments of said plural data segments have not been analyzed.

4. The method of claim 3 further comprising the step of:

(g) confirming by the apparatus, after said step (d) and before said step (e), accuracy of the identification of the data element stored at said step (d) by vocalizing the stored identified data element to the user.

5. A method for enabling selective revision of all data elements identified from user vocalized speech data by an automated speech recognition apparatus through use of a predetermined spoken command issued by a user, comprising the steps of:

(a) prompting by the apparatus for user input of vocalized speech data comprising a plurality of speech data segments each representative of a data element;

(b) receiving by the apparatus one of the user vocalized speech data segments of said plural speech data segments;

(c) analyzing in the apparatus the received vocalized speech data segment to identify a data element corresponding to the received vocalized speech data segment;

(d) storing the identified data element in a memory of the apparatus;

(e) after storing of the identified data element in the memory of the apparatus, deleting by the apparatus all identified data elements previously stored in the memory of the apparatus and returning to said step (a) when the predetermined spoken command, representing a user-vocalized request that input of all previously stored identified data elements is to be repeated, is issued by the user and received by the apparatus; and

(f) after said step (d) and absent receipt of said predetermined user-issued command, determining by the apparatus whether all speech data segments of said plural data segments have been analyzed, and returning to said step (b) if all speech data segments of said plural data segments have not been analyzed.

6. The method of claim 5 further comprising the step of:

(g) confirming by the apparatus, after said step (d) and before said step (e), accuracy of the identification of the data element stored at said step (d) by vocalizing the stored identified data element to the user.